feat(migration): phase 1 — Session + Tracer + RunConfig factory

Three foundation modules per PLAYBOOK §2.8 / §2.9 / §2.10 with all
relevant R2/R3 corrections (C7, C10, C11, C16, C21):

  strix/llm/strix_session.py            SessionABC wrapper around the
                                        legacy MemoryCompressor; on any
                                        compression failure, returns
                                        uncompressed history and
                                        permanently disables compression
                                        for the rest of the run (C10 +
                                        Round 3.4 W5/E2).

  strix/telemetry/strix_processor.py    SDK TracingProcessor that writes
                                        events.jsonl in our schema. All
                                        hooks SYNC per ABC (F3); writes
                                        protected by per-path
                                        threading.Lock (C7); OSError
                                        swallowed and logged (C16); PII
                                        scrubbed via the existing
                                        TelemetrySanitizer.

  strix/run_config_factory.py           make_run_config() with our
                                        defaults: parallel_tool_calls=
                                        False (C1 Phase-1 safe default),
                                        retry policy explicitly excludes
                                        401/403/400 (C11), reasoning
                                        effort + model_settings_override
                                        merge path (C21).
                                        make_agent_context() returns the
                                        canonical per-agent dict
                                        including is_whitebox/diff_scope/
                                        run_id (C21).

32 new smoke tests (197/197 total). mypy strict + ruff clean. Per-file
ignores added for tests/** S105/PT018 and for the two new src modules'
intentional broad-Exception catches (BLE001).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

strix/run_config_factory.py

@@ -0,0 +1,206 @@
+"""make_run_config — assemble a Strix-flavored ``RunConfig`` for ``Runner.run``.
+
+Factory pattern: every Strix scan goes through here so the defaults are
+applied uniformly. Per-call overrides are accepted via ``model_settings_override``
+for the rare case a single run wants different reasoning effort or
+``tool_choice`` (C21).
+
+References:
+    - PLAYBOOK.md §2.10
+    - AUDIT.md §2.1 (C1 — parallel_tool_calls=False until Phase 6 relaxes the
+      legacy tool server's per-agent task slot serialization)
+    - AUDIT_R2.md §1.6 (C11 — retry policy explicitly excludes 401/403/400;
+      auth and validation errors must fail fast, not waste retries)
+    - AUDIT_R3.md C21 — RunConfig override + context fields including
+      ``is_whitebox``, ``diff_scope``, ``run_id``
+"""
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Any, Literal
+
+from agents import RunConfig
+from agents.model_settings import ModelSettings
+from agents.retry import (
+    ModelRetryBackoffSettings,
+    ModelRetrySettings,
+    retry_policies,
+)
+from agents.sandbox import SandboxRunConfig
+
+from strix.llm.multi_provider_setup import build_multi_provider
+from strix.orchestration.filter import inject_messages_filter
+
+
+if TYPE_CHECKING:
+    from agents.sandbox.session.base_sandbox_session import BaseSandboxSession
+
+    from strix.orchestration.bus import AgentMessageBus
+
+
+# Phase 1-5 default. Phase 6 relaxes the legacy tool server's per-agent
+# task-slot serialization (``runtime/tool_server.py:94-97``) and flips this
+# to ``True`` after the multi-agent stress tests confirm safety.
+_PHASE1_PARALLEL_DEFAULT = False
+
+# Default retry policy. Explicitly does NOT include 401/403/400 — those are
+# auth and validation errors that retrying cannot fix; they should fail fast
+# so the user sees the real error within seconds. 429/5xx is the right set.
+_RETRYABLE_HTTP_STATUSES = (429, 500, 502, 503, 504)
+
+# Default retry budget. Mirrors the legacy ``llm.py`` retry loop: 5 attempts
+# with ``min(90, 2*2^n)`` backoff.
+_DEFAULT_MAX_RETRIES = 5
+_DEFAULT_BACKOFF = ModelRetryBackoffSettings(
+    initial_delay=2.0,
+    max_delay=90.0,
+    multiplier=2.0,
+    jitter=False,
+)
+
+
+def _default_retry_policy() -> Any:
+    """Build the default retry policy.
+
+    Built from ``retry_policies.any(...)``: any of the listed conditions
+    triggers a retry. ``provider_suggested`` honors server-sent
+    ``Retry-After`` hints; ``network_error`` covers connection / timeout;
+    ``http_status`` whitelists transient HTTP codes.
+    """
+    return retry_policies.any(
+        retry_policies.provider_suggested(),
+        retry_policies.network_error(),
+        retry_policies.http_status(_RETRYABLE_HTTP_STATUSES),
+    )
+
+
+#: Default ``max_turns`` callers should pass to ``Runner.run``.
+#: Mirrors the legacy ``AgentState.max_iterations = 300``
+#: (``HARNESS_WIKI.md §5.2``).
+STRIX_DEFAULT_MAX_TURNS = 300
+
+
+def make_run_config(
+    *,
+    sandbox_session: BaseSandboxSession | None,
+    model: str = "strix/claude-sonnet-4.6",
+    parallel_tool_calls: bool = _PHASE1_PARALLEL_DEFAULT,
+    tool_choice: Literal["auto", "required", "none"] | None = "required",
+    reasoning_effort: Literal["low", "medium", "high"] | None = None,
+    model_settings_override: ModelSettings | None = None,
+    sandbox_client: Any | None = None,
+) -> RunConfig:
+    """Build a ``RunConfig`` with Strix defaults.
+
+    Note: ``max_turns`` and ``isolate_parallel_failures`` are NOT
+    ``RunConfig`` fields — they are passed directly to ``Runner.run``.
+    Use ``STRIX_DEFAULT_MAX_TURNS`` for the budget; pass
+    ``isolate_parallel_failures=False`` to ``Runner.run`` if Phase 6 has
+    not yet flipped ``parallel_tool_calls=True``.
+
+    Args:
+        sandbox_session: Live sandbox session shared by every agent in this
+            scan (one container per scan; see ``strix.sandbox.session_manager``).
+            ``None`` is allowed for unit tests and dry runs.
+        model: Model alias to pass to ``MultiProvider``. Defaults to the
+            current production-favored Anthropic alias.
+        parallel_tool_calls: Phase 1 default is ``False`` to keep behavior
+            sequential per the legacy tool server's slot serialization (C1).
+        tool_choice: Forces tool use per turn unless explicitly relaxed.
+            Mirrors the legacy ``4f90a56`` prompt hardening at the model
+            level. Pass ``None`` to omit.
+        reasoning_effort: ``"low" | "medium" | "high"``; routes to
+            ``ModelSettings.reasoning``. ``None`` defers to provider default.
+        model_settings_override: Optional ``ModelSettings`` to merge over
+            the factory defaults (C21 — per-run override path).
+        sandbox_client: Optional pre-built sandbox client (e.g., the Strix
+            Docker subclass). Defaults to ``None``; the SDK will instantiate
+            its built-in if a session is supplied without a client.
+
+    Returns:
+        A ``RunConfig`` ready to pass to ``Runner.run``.
+    """
+    base_settings = ModelSettings(
+        parallel_tool_calls=parallel_tool_calls,
+        tool_choice=tool_choice,
+        retry=ModelRetrySettings(
+            max_retries=_DEFAULT_MAX_RETRIES,
+            backoff=_DEFAULT_BACKOFF,
+            policy=_default_retry_policy(),
+        ),
+    )
+    if reasoning_effort is not None:
+        from openai.types.shared import Reasoning
+
+        base_settings = base_settings.resolve(
+            ModelSettings(reasoning=Reasoning(effort=reasoning_effort)),
+        )
+    if model_settings_override is not None:
+        # ``ModelSettings.resolve`` merges another ModelSettings into self
+        # with override-wins semantics — exactly what we want.
+        base_settings = base_settings.resolve(model_settings_override)
+
+    sandbox_config = (
+        SandboxRunConfig(client=sandbox_client, session=sandbox_session)
+        if sandbox_session is not None
+        else None
+    )
+
+    return RunConfig(
+        model=model,
+        model_provider=build_multi_provider(),
+        model_settings=base_settings,
+        sandbox=sandbox_config,
+        call_model_input_filter=inject_messages_filter,
+        tracing_disabled=False,
+        trace_include_sensitive_data=False,
+    )
+
+
+def make_agent_context(
+    *,
+    bus: AgentMessageBus,
+    sandbox_session: BaseSandboxSession | None,
+    sandbox_token: str | None,
+    tool_server_host_port: int | None,
+    caido_host_port: int | None,
+    agent_id: str,
+    agent_name: str,
+    parent_id: str | None,
+    tracer: Any | None,
+    model: str = "strix/claude-sonnet-4.6",
+    model_settings: ModelSettings | None = None,
+    max_turns: int = 300,
+    is_whitebox: bool = False,
+    diff_scope: dict[str, Any] | None = None,
+    run_id: str | None = None,
+) -> dict[str, Any]:
+    """Build the per-agent ``context`` dict passed to ``Runner.run(context=...)``.
+
+    The dict is the canonical place where bus, sandbox handles, identity,
+    tracer reference, and per-agent toggles live. Tools, hooks, and the
+    ``inject_messages_filter`` all reach in via ``ctx.context.get(...)``.
+
+    C21 (AUDIT_R3): includes ``is_whitebox``, ``diff_scope`` and ``run_id``
+    fields that the legacy code relied on but the original PLAYBOOK §2.10
+    skeleton omitted.
+    """
+    return {
+        "bus": bus,
+        "sandbox_session": sandbox_session,
+        "sandbox_token": sandbox_token,
+        "tool_server_host_port": tool_server_host_port,
+        "caido_host_port": caido_host_port,
+        "agent_id": agent_id,
+        "agent_name": agent_name,
+        "parent_id": parent_id,
+        "tracer": tracer,
+        "model": model,
+        "model_settings": model_settings,
+        "max_turns": max_turns,
+        "turn_count": 0,
+        "agent_finish_called": False,
+        "is_whitebox": is_whitebox,
+        "diff_scope": diff_scope,
+        "run_id": run_id,
+    }